Deep Learning in Graph Domains for Sensorised Environments

In the future, robots and smart environments will cooperate to assist people, performing monitoring tasks to enhance people’s comfort and safety. These environments are characterised by a large number of sensors generating vast amounts of interrelated data that are naturally expressed as graphs. The predominant approach to deal with graph structures is two-stage. In the first stage, input data is transformed into vectors. In the second stage, vectors are processed to learn and extract conclusions. Unfortunately, valuable information is generally lost in the graph-to-vector conversion. Techniques natively working with graph-representations are a less explored approach. This PhD will focus on enabling robots and environment sensors to share a common graph-like world model representation and to perform reasoning tasks using machine learning techniques specially designed to work with graph structures.
Collaborator: Ortelio Ltd.

Further information: https://jobs.aston.ac.uk/Vacancy.aspx?ref=R190198